RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can OLMo 2 0425 1B run on the Mac M3 24GB?

Yes. At 8K context the best fit is F16, using about 4.4 GB of the 16.1 GB usable on the Mac M3 24GB. Estimated speed ceiling: ~34 tokens/sec.

Memory by quant and context

Quant4K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •1.7 GB Fits158
3-bit (Q3_K_M) •1.8 GB Fits128
4-bit (Q4_K_M) •2.0 GB Fits107
5-bit (Q5_K_M) •2.1 GB Fits93
6-bit (Q6_K) •2.2 GB Fits82
8-bit (Q8_0) •2.6 GB Fits63
16-bit (F16/BF16) •3.9 GB Fits34

• real GGUF file size from allenai/OLMo-2-0425-1B-GGUF. Speed is a bandwidth ceiling (100 GB/s), not a benchmark. Methodology.

What fits instead

"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.

More

OLMo 2 0425 1B on every GPU and Mac · Every model that runs on the Mac M3 24GB · Apple Silicon guide · Try other settings in the calculator

Data: Hugging Face Hub (allenai/OLMo-2-0425-1B), Apple specs. Model data last checked 2026-11-17; refreshed hourly.